Real-Time AI Inference Engineer — Remote

ElevenLabs; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

ElevenLabs is seeking a Research Engineer to join the research team, focused on deploying frontier AI models in production. You will own systems that turn research breakthroughs into real-time products used by millions, delivering fast, reliable serving.

You will optimize latency, throughput, and cost with techniques like quantization, distillation, caching, and custom kernels, and you will build tooling to ship new models safely and confidently.

Qualifications

• Experience deploying and serving ML models in production.
• Strong engineering skills in GPU programming and inference optimization.
• Ability to profile and diagnose bottlenecks across the serving stack.

Responsibilities

• Deploy state-of-the-art models to production and own the path from research checkpoint to serving infrastructure.
• Optimize inference performance across latency, throughput, and cost using advanced techniques.
• Build high-performance serving systems for real-time, streaming workloads.
• Create tooling and infrastructure enabling researchers to ship new models quickly and safely.

Skills

GPU programming

Inference optimization

Profiling & bottlenecks

Real-time systems

Python

Tools

CUDA

Triton

TensorRT

vLLM

SGLang

Job description

ElevenLabs is seeking a Research Engineer to join the research team, focused on deploying frontier AI models in production. You will own systems that turn research breakthroughs into real-time products used by millions, delivering fast, reliable serving.

You will optimize latency, throughput, and cost with techniques like quantization, distillation, caching, and custom kernels, and you will build tooling to ship new models safely and confidently.